Basic Statistics - Defining and Collecting Data

Comprehensive practice flashcards covering introductory statistics concepts from STAT6171 Session 1, including data vs. variables, measurement scales, sampling methodologies, and sources of survey error.

What textbook is used for the course STAT6171 - Basic Statistics?

Statistics for Managers using Microsoft Excel ($8^{\text{th}}$ Edition) by David M. Levine, David F. Stephan, and Kathryn A. Szabat (Pearson).

What is the distinction between statistik and statistika?

Statistik is a collection of data, numbers, or information, whereas statistika is the scientific discipline that studies how data and numbers are collected, processed, and analyzed to produce actionable information for decision-making.

How is descriptive statistics (statistika deskriptif) defined?

The branch of statistics concerned with summarizing or describing data concisely so that it is easier to read, interpret, and understand meaningfully.

How is inferential statistics (statistika inferential) defined?

The branch of statistics concerned with analyzing and studying a sample to draw conclusions or inferences about an entire population.

In research methodology, what is a variable?

The object of research, or the specific focal point and topic of attention within an investigation.

In research methodology, what is data?

The recorded results of research observation or measurement, presented in the form of either facts or numerical figures.

What is a quantitative variable (variabel kuantitatif)?

A variable that represents an amount or numerical quantity that can be counted or measured, such as classroom size, age, or height.

What is a qualitative variable (variabel kualitatif)?

A categorical variable that adopts names or descriptive labels to place observations into distinct groups, such as eye color or gender.

What is a discrete variable (variabel diskrit), and how is it acquired?

A numerical variable obtained strictly from the process of counting (hasil perhitungan), such as the count of passing vehicles or enrolled students.

What is a continuous variable (variabel kontinu), and how is it acquired?

A numerical variable obtained strictly through physical measurement (hasil pengukuran), such as temperature, weight, or height.

What distinct properties characterize a nominal measurement scale?

It only possesses the classification or grouping property (pengelompokan), lacking any intrinsic ranking, standard distance, or absolute zero.

What distinct properties characterize an ordinal measurement scale?

It possesses grouping (pengelompokan) and order or rank (tingkatan/urutan), but lacks consistent interval distances and an absolute zero.

What distinct properties characterize an interval measurement scale?

It includes grouping, order, and measurable differences or distances (jarak), but lacks a true absolute zero ($\text{nol mutlak}$), meaning ratios or multiples cannot be established.

What distinct properties characterize a ratio measurement scale?

It includes all four measurement properties: grouping, ranking, equal distances, and a true absolute zero ($\text{nol mutlak}$), allowing mathematical multiples and ratios to be determined.

What is the definition of a population in statistics?

All items, elements, or individuals that are the target of observation and investigation in a study.

What is the definition of a sample in statistics?

A subset or portion selected from a population to be investigated because it is deemed representative of that entire population.

What are the primary data collection methods listed in the lecture?

Experiments, census surveys, direct observations, and interviews.

What secondary data sources are identified in the lecture?

Books, scholarly journals, and official government publications.

What defines probability sampling and what is its prerequisite?

A selection technique wherein every element within the population has an equal opportunity of being chosen using probability rules; it strictly requires an existing sampling frame (kerangka sampel).

What is simple random sampling, and what conditions are required to execute it?

A probability sampling method using lotteries or random number tables; it requires an available sampling frame, a homogeneous population, and a population that is not overly dispersed geographically.

How is stratified random sampling implemented?

By partitioning the target population into distinct subgroups known as strata, and then taking a random sample independently from each stratum.

What is cluster sampling?

A probability sampling design in which the population is divided into heterogeneous subgroups (clusters) that share similar internal structures and elements across clusters.

How does systematic sampling select elements from a list?

It selects every $k^{\text{th}}$ unit from an ordered sampling frame starting from an initial random selection, yielding elements $1, 1+k, 1+2k, \dots, 1+(n-1)k$.

What is haphazard sampling, and why does it fail to represent the population?

A non-probability method selecting units based on researcher convenience rather than representativeness (such as person-on-the-street interviews); its findings cannot be generalized to any broader population.

How does snowball sampling operate?

A non-probability sampling method where respondents provide referrals or information to identify subsequent participants sequentially until enough data is collected.

What is purposive sampling (judgment sampling)?

A non-probability sampling technique where units are deliberately handpicked based on predefined criteria or specific judgments to obtain cases with desired attributes.

What are the five main sources of error in survey collection?

The interviewer, the respondent, the measuring apparatus (alat ukur), the data collection method, and environmental conditions (alam).

What characterizes gross errors (kesalahan kasar) in survey measurements, and how can they be minimized?

Mistakes arising from carelessness, inattention, or lack of experience (such as reading or recording incorrectly); they can be prevented by repeating measurements, applying specific measurement protocols, and having $2$ or more individuals conduct the measurement.

What causes systematic errors (kesalahan sistematik) in survey measurements, and how are they avoided?

Flaws stemming from the measuring instruments themselves (e.g., incorrect scale intervals, tape length) or improper measurement procedures; they are avoided by calibrating instruments before use, following standard procedures, and applying mathematical corrections during data processing.

What causes random errors (kesalahan random/tak terduga) in survey measurements?

Unpredictable environmental fluctuations such as atmospheric vibrations, unstable ground where the device stands, wind velocity, or shifting observation conditions during repeated measurements.