Research Theory Week 10

A new research study is trying to understand how undergraduate students utilize textbooks. Results of previous studies have shown that publishers believe students prefer online textbooks, while educators believe students still prefer printed textbooks if they buy textbooks at all. Since undergraduate students are usually very close in age, the researchers decide not to create age groups and instead ask an open ended question to assess respondents' age. Once the data is collected, the researcher can create a grouping variable based on the age distribution of the sample.   What is the process called that researchers will implement to change the data by creating a grouping variable?   a. Data transferal b. Data transformation c. Statistical base d. Data elaboration

Which modeling techniques are suitable to build a predictive model ? (Multiple answer may be correct)   Group of answer choices Multiple linear regression Classification tree Logistic regression Clustering

Which best describes the null hypothesis associated with an Analysis of Variance (ANOVA)?   Group of answer choices a. Ho:  Variance 1 = Variance 2 = Variance 3 b. Ho:  Standard Deviation 1 = Standard Deviation 2 = Standard Deviation 3 c. Ho:  Proportion 1 = Proportion 2 = Proportion 3 d. Ho:  Median 1 = Median 2 = Median 3 e. Ho:  Mean 1 = Mean 2 = Mean 3

Discuss at least 2 different data collection methods you could use.  What are the differences between probability and nonprobability sampling methods?

A marketing director would like to estimate the effect of advertising expenditures on the quantity of his product sold controlling for the effects of price and average household income in the area. The dependent variable in this regression should be: A) price B) average household income C) quantity sold D) advertising expenditure

In the sampling, hypothesis testing and analysis of business research data, which of the following is true?   Group of answer choices 1. We make inferences about the population parameters based on sample statistics 2. The sample should be representative of the population 3. A larger sample size is always better 4. Answers1 and 2 only 5. Answers 1, 2 and 3

According to Stuart (2010), which of the following statements about observational study designs for causal inference are typically true? Choose all that apply. Including propensity score estimates as a predictor in a regression model on outcomes can help resolve imbalance between treatment and control groups for covariates used in the propensity score model Standard diagnostic tools for binary prediction or classification models (e.g. logistic regression or classification trees) are similarly used in evaluating propensity score estimates When conditional ignorability holds given the observed covariates, then the treatment assignment will also be ignorable conditioned on the propensity scores Overfitting in propensity score estimation can achieve more efficient estimates of treatment effects than using propensity score estimates that are closer to the true propensities Unlike full matching, subclassification, and weighting methods, nearest neighbor matching does not necessarily use all…

snip

The following time series represents the number of automobiles sold by a car dealership each of the past five months. t 1 2 3 4 5 Yt 7 12 10 13 14 (a) Construct a time series plot. What type of pattern exists in the data? The time series plot shows a linear trend.The time series plot shows a horizontal pattern.    The time series plot shows a seasonal pattern.The time series plot shows a nonlinear trend.   (b) Use simple linear regression analysis to find the parameters for the line that minimizes MSE for this time series. t =        (c) What is the forecast for  t = 6?

Consider the following hypothesis test: Ho: µ 2 45 Ha: µ < 45 A sample of 36 is used. Identify the p-value and state your conclusion for each of the following sample results. Use a = 0.01. a. With = 44 and s = 5.2, the p-value is - Select your answer - Can it be concluded that the population mean is less than 45 ? |- Select your answer - b. With = 43 and s = 4.6, the p-value is - Select your answer Can it be concluded that the population mean is less than 45? Select your answer - c. With a = 46 and s = 5, the p-value is - Select your answer - Can it be concluded that the population mean is less than 45? |- Select your answer -

1,